© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118180
    Prev
    Next
    INDEX
    Explanations

    after developer conference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    なかった
    -0.06
     감소
    -0.06
     பாதுகா
    -0.06
    ✊
    -0.06
     mancan
    -0.06
     ආරක්ෂ
    -0.06
     segurança
    -0.06
     बचाने
    -0.06
    udal
    -0.06
     során
    -0.06
    POSITIVE LOGITS
    apprentissage
    0.06
    After
    0.06
     apprenticeship
    0.06
     after
    0.05
     donkey
    0.05
    後に
    0.05
     стиль
    0.05
    ጅ
    0.05
    after
    0.05
     waitress
    0.05
    Activations Density 0.005%

    No Known Activations